Files
crewAI/tests/cassettes/test_agent_human_input.yaml
Brandon Hancock (bhancock_ai) 611526596a Brandon/cre 509 hitl multiple rounds of followup (#1702)
* v1 of HITL working

* Drop print statements

* HITL code more robust. Still needs to be refactored.

* refactor and more clear messages

* Fix type issue

* fix tests

* Fix test again

* Drop extra print
2024-12-05 10:14:04 -05:00

435 lines
15 KiB
YAML

interactions:
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
is the expect criteria for your final answer: The word: Hi\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '824'
content-type:
- application/json
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AaqIIsTxhvf75xvuu7gQScIlRSKbW\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344190,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"I now can give a great answer \\nFinal
Answer: Hi\",\n \"refusal\": null\n },\n \"logprobs\": null,\n
\ \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
158,\n \"completion_tokens\": 12,\n \"total_tokens\": 170,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8cfc3b1f4532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:50 GMT
Server:
- cloudflare
Set-Cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
path=/; expires=Wed, 04-Dec-24 20:59:50 GMT; domain=.api.openai.com; HttpOnly;
Secure; SameSite=None
- _cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000;
path=/; domain=.api.openai.com; HttpOnly; Secure; SameSite=None
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '313'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999816'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_9fd9a8ee688045dcf7ac5f6fdf689372
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "Determine if the following
feedback indicates that the user is satisfied or if further changes are needed.
Respond with ''True'' if further changes are needed, or ''False'' if the user
is satisfied. **Important** Do not include any additional commentary outside
of your ''True'' or ''False'' response.\n\nFeedback: \"Don''t say hi, say Hello
instead!\""}], "model": "gpt-4o-mini", "stop": ["\nObservation:"], "stream":
false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '461'
content-type:
- application/json
cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AaqIIaQlLyoyPmk909PvAIfA2TmJL\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344190,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"True\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 78,\n \"completion_tokens\":
1,\n \"total_tokens\": 79,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8d060b5e4532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:50 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '375'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999898'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_be7cb475e0859a82c37ee3f2871ea5ea
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "You are test role. test backstory\nYour
personal goal is: test goal\nTo give my best complete final answer to the task
use the exact following format:\n\nThought: I now can give a great answer\nFinal
Answer: Your final answer must be the great and the most complete as possible,
it must be outcome described.\n\nI MUST use these formats, my job depends on
it!"}, {"role": "user", "content": "\nCurrent Task: Say the word: Hi\n\nThis
is the expect criteria for your final answer: The word: Hi\nyou MUST return
the actual complete content as the final answer, not a summary.\n\nBegin! This
is VERY important to you, use the tools available and give your best Final Answer,
your job depends on it!\n\nThought:"}, {"role": "assistant", "content": "I now
can give a great answer \nFinal Answer: Hi"}, {"role": "user", "content": "Feedback:
Don''t say hi, say Hello instead!"}], "model": "gpt-4o-mini", "stop": ["\nObservation:"],
"stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '986'
content-type:
- application/json
cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AaqIJAAxpVfUOdrsgYKHwfRlHv4RS\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344191,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"Thought: I now can give a great answer
\ \\nFinal Answer: Hello\",\n \"refusal\": null\n },\n \"logprobs\":
null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\":
188,\n \"completion_tokens\": 14,\n \"total_tokens\": 202,\n \"prompt_tokens_details\":
{\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\":
{\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8d090fc34532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:51 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '484'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999793'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5bf4a565ad6c2567a1ed204ecac89134
http_version: HTTP/1.1
status_code: 200
- request:
body: '{"messages": [{"role": "system", "content": "Determine if the following
feedback indicates that the user is satisfied or if further changes are needed.
Respond with ''True'' if further changes are needed, or ''False'' if the user
is satisfied. **Important** Do not include any additional commentary outside
of your ''True'' or ''False'' response.\n\nFeedback: \"looks good\""}], "model":
"gpt-4o-mini", "stop": ["\nObservation:"], "stream": false}'
headers:
accept:
- application/json
accept-encoding:
- gzip, deflate
connection:
- keep-alive
content-length:
- '439'
content-type:
- application/json
cookie:
- __cf_bm=QJZZjZ6eqnVamqUkw.Bx0mj7oBi3a_vGEH1VODcUxlg-1733344190-1.0.1.1-xyN0ekA9xIrSwEhRBmTiWJ3Pt72UYLU5owKfkz5yihVmMTfsr_Qz.ssGPJ5cuft066v1xVjb4zOSTdFmesMSKg;
_cfuvid=eCIkP8GVPvpkg19eOhCquWFHm.RTQBQy4yHLGGEAH5c-1733344190334-0.0.1.1-604800000
host:
- api.openai.com
user-agent:
- OpenAI/Python 1.52.1
x-stainless-arch:
- arm64
x-stainless-async:
- 'false'
x-stainless-lang:
- python
x-stainless-os:
- MacOS
x-stainless-package-version:
- 1.52.1
x-stainless-raw-response:
- 'true'
x-stainless-retry-count:
- '0'
x-stainless-runtime:
- CPython
x-stainless-runtime-version:
- 3.12.7
method: POST
uri: https://api.openai.com/v1/chat/completions
response:
content: "{\n \"id\": \"chatcmpl-AaqIJqyG8vl9mxj2qDPZgaxyNLLIq\",\n \"object\":
\"chat.completion\",\n \"created\": 1733344191,\n \"model\": \"gpt-4o-mini-2024-07-18\",\n
\ \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\":
\"assistant\",\n \"content\": \"False\",\n \"refusal\": null\n
\ },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n
\ ],\n \"usage\": {\n \"prompt_tokens\": 73,\n \"completion_tokens\":
1,\n \"total_tokens\": 74,\n \"prompt_tokens_details\": {\n \"cached_tokens\":
0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n
\ \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\":
0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\":
\"fp_0705bf87c0\"\n}\n"
headers:
CF-Cache-Status:
- DYNAMIC
CF-RAY:
- 8ece8d0cfdeb4532-ATL
Connection:
- keep-alive
Content-Encoding:
- gzip
Content-Type:
- application/json
Date:
- Wed, 04 Dec 2024 20:29:51 GMT
Server:
- cloudflare
Transfer-Encoding:
- chunked
X-Content-Type-Options:
- nosniff
access-control-expose-headers:
- X-Request-ID
alt-svc:
- h3=":443"; ma=86400
openai-organization:
- crewai-iuxna1
openai-processing-ms:
- '341'
openai-version:
- '2020-10-01'
strict-transport-security:
- max-age=31536000; includeSubDomains; preload
x-ratelimit-limit-requests:
- '30000'
x-ratelimit-limit-tokens:
- '150000000'
x-ratelimit-remaining-requests:
- '29999'
x-ratelimit-remaining-tokens:
- '149999902'
x-ratelimit-reset-requests:
- 2ms
x-ratelimit-reset-tokens:
- 0s
x-request-id:
- req_5554bade8ceda00cf364b76a51b708ff
http_version: HTTP/1.1
status_code: 200
version: 1